© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18102
    Prev
    Next
    INDEX
    Explanations

    prospective clients or candidates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brass
    -0.08
    -0.07
     mac
    -0.07
     entrenched
    -0.07
    prog
    -0.07
     strut
    -0.07
     portions
    -0.07
     Brad
    -0.07
    iqu
    -0.06
    erner
    -0.06
    POSITIVE LOGITS
     buyers
    0.23
     customers
    0.21
     purchasers
    0.19
     clients
    0.18
     Buyers
    0.18
     buyer
    0.17
     Customers
    0.17
     applicants
    0.17
     candidates
    0.17
     employers
    0.17
    Activations Density 0.078%

    No Known Activations